Topic
Object (computer science)
About: Object (computer science) is a research topic. Over the lifetime, 106024 publications have been published within this topic receiving 1360115 citations. The topic is also known as: obj & Rq.
Papers published on a yearly basis
Papers
More filters
15 Jun 2019
TL;DR: In this paper, a generative shape proposal network (GSPN) is proposed for instance segmentation in point cloud data, which takes an analysis-by-synthesis strategy and generates proposals by reconstructing shapes from noisy observations in a scene.
Abstract: We introduce a novel 3D object proposal approach named Generative Shape Proposal Network (GSPN) for instance segmentation in point cloud data. Instead of treating object proposal as a direct bounding box regression problem, we take an analysis-by-synthesis strategy and generate proposals by reconstructing shapes from noisy observations in a scene. We incorporate GSPN into a novel 3D instance segmentation framework named Region-based PointNet (R-PointNet) which allows flexible proposal refinement and instance segmentation generation. We achieve state-of-the-art performance on several 3D instance segmentation tasks. The success of GSPN largely comes from its emphasis on geometric understandings during object proposal, greatly reducing proposals with low objectness.
308 citations
Patent•
IBM1
TL;DR: In this paper, a method, system, and computer program product for caching dynamically generated content (including, but not limited to, dynamically generated Web pages), as well as determining when the cached content should be invalidated or purged.
Abstract: A method, system, and computer program product for caching dynamically generated content (including, but not limited to, dynamically generated Web pages), as well as determining when the cached content should be invalidated or purged. Rather than caching the generated datastream (i.e. the end result of the computations used in the dynamic generation process) as in the prior art, the interim results of computations (such as a generated bean instance or object, where the interim results may be stored using properties and methods) are cached according to the present invention. The input properties used to generate the bean or object, along with the input property values, are used to distinguish among cached instances and thereby identify when a cached instance may be used to respond to a subsequent request for the same content. Re-execution of the business logic of the bean or object may then be avoided, using the cached bean's or object's output properties to generate the content response. Application-specific, developer-defined criteria may be used in the cache invalidation determination.
308 citations
Book•
01 Jan 1988TL;DR: The Synthesizer Generator is ideal for use in course projects and should be of particular interest to those involved in compiler construction, and the book contains a wealth of material for those building specialized editors "by hand", without using an editor-generating tool.
Abstract: The Synthesizer Generator: A System for Constructing Language-Based Editors presents a detailed account of the Synthesizer Generator, a system for automating the construction of customized editors for particular languages. The unique feature of the Synthesizer Generator is its use of an immediate-computation paradigm to perform analysis, translation, and error reporting while an object is being edited. With the Synthesizer Generator one can create programming language environments that incrementally parse, type-check, and compile a program as it is interactively developed. The use of the system is not restricted to programming languages; editors for logics, specification languages, and verification languages can be created as well. The specification language of the Synthesizer Generator is based on the attribute-grammar concept, which plays a major role in the way compiler construction is taught today. For this reason, the Synthesizer Generator is ideal for use in course projects and should be of particular interest to those involved in compiler construction. The Synthesizer Generator is also intended for readers with an interest in software tools and methods for building interactive systems. More than just a user guide for the system, the book contains a wealth of material for those building specialized editors "by hand", without using an editor-generating tool; it discusses the issues that motivated the decisions made in the design of the system, as well as a number of the algorithms used in the system's implementation.
308 citations
Patent•
12 Jan 2010
TL;DR: In this paper, a method of operating a dimensioning system to determine dimensional information for objects is disclosed, where a number of images are acquired and objects in at least one of the acquired images are computationally identified.
Abstract: A method of operating a dimensioning system to determine dimensional information for objects is disclosed. A number of images are acquired. Objects in at least one of the acquired images are computationally identified. One object represented in the at least one of the acquired images is computationally initially selected as a candidate for processing. An indication of the initially selected object is provided to a user. At least one user input indicative of an object selected for processing is received. Dimensional data for the object indicated by the received user input is computationally determined.
306 citations
TL;DR: The main object of as discussed by the authors is to provide the logical machinery needed for a viable basis for talking of the "consequences", the "content" or of "equivalences" between inconsistent sets of premisses.
Abstract: The main object of this paper is to provide the logical machinery needed for a viable basis for talking of the ‘consequences’, the ‘content’, or of ‘equivalences’ between inconsistent sets of premisses.
306 citations